Robust optimization for smart demand side management in microgrids using robotic process automation and grey wolf optimization

Abstract

The increasing variability in energy demand and the adoption of renewable energy sources have made microgrids critical for sustainable energy management. However, the unpredictability of renewable generation and fluctuating load demand presents significant challenges in achieving reliable and cost-effective operations. This paper proposes a Robotic Process Automation (RPA) driven energy management framework with a focus on demand-side control to optimize microgrid performance under uncertainty. The framework combines RPA's automation capabilities with the Grey Wolf Optimizer (GWO) to dynamically balance supply and demand. Key innovations include real-time load scheduling, demand response optimization, and integration of controllable and non-controllable loads, enhancing flexibility and efficiency. By automating tasks such as data aggregation, scenario generation, and control execution, the framework reduces manual intervention and improves system adaptability. Simulation results show that the framework achieves significant improvements, including a reduction in emissions by 10%, a 15% reduction in operational costs, and a 20% increase in power supply reliability. Moreover, it demonstrates flexibility across varying priorities, with the lowest total cost achieved in emission-focused scenarios (F = 168.10) and balanced performance in mixed-priority cases (F = 195.85). These findings underscore the framework's ability to adapt to diverse stakeholder objectives and highlight its potential to revolutionize demand-side energy management, fostering efficient and sustainable microgrid operations.